Notifications
Clear all
Topic starter
14/08/2026 6:37 pm
TL;DR: RFC 8693 token exchange lets AI agents use delegated, scoped credentials with explicit on-behalf-of semantics, instead of durable tokens that blur accountability, according to Oleria Security. The real shift is architectural: agent identity becomes auditable only when privilege is exchanged per call, not assumed at session start.
NHIMG editorial — based on content published by Oleria Security: why the agent gateway was built on RFC 8693
By the numbers:
- Only 5.7% of organisations have full visibility into their service accounts.
- 91.6% of secrets remain valid five days after the targeted organisation is notified, showing a critical gap in remediation procedures.
- 92% of organisations expose NHIs to third parties, raising concerns about supply chain security.
Questions worth separating out
Q: How should security teams govern AI agents that can access enterprise systems?
A: Security teams should govern AI agents as non-human identities with explicit ownership, scoped privileges, and continuous monitoring.
Q: Why do AI agents break traditional token and session models?
A: Traditional models assume the same credential can safely persist across many calls, but agents often chain actions, tools, and audiences within one session.
Q: When should organisations replace durable agent credentials with token exchange?
A: Replace durable agent credentials when the agent can reach multiple tools, touch regulated data, or trigger actions that require attribution.
Practitioner guidance
- Map agent flows to delegation boundaries Inventory where agents currently reuse session tokens, where OAuth exchange is available, and where a downstream API still accepts broad bearer credentials.
- Require actor and subject context in every token Make subject_token, actor_token, and auditable act-style claims mandatory for sensitive agent calls so investigators can reconstruct who authorized what.
- Bind each token to one audience and one task Reject agent tokens that can be replayed across tools or business functions.
What's in the full article
Oleria Security's full post covers the operational detail this post intentionally leaves for the source:
- How the authorizer evaluates subject and actor tokens before issuing scoped access for agent calls.
- Implementation details for policy, revocation, and audit logging around RFC 8693 exchanges.
- How the gateway translates token exchange semantics across MCP servers, OAuth services, and bespoke APIs.
- The specific claims and token fields the vendor uses to preserve on-behalf-of attribution.
👉 Read Oleria Security's analysis of RFC 8693 for AI agent identity →
RFC 8693 token exchange for AI agents: what IAM teams need?
Explore further
View Full Forum → | NHI Foundation Course → | Our Services →
14/08/2026 6:43 pm
RFC 8693 is becoming the control plane for agent delegation, not just an OAuth extension. The article is right to treat token exchange as the architectural answer to agent accountability because durable bearer tokens collapse under delegated runtime action. For security leaders, the practical consequence is that agent identity should be governed as an exchange problem, not a static credential problem.
A few things that frame the scale:
- Only 5.7% of organisations have full visibility into their service accounts, according to Ultimate Guide to NHIs.
- 92% of organisations expose NHIs to third parties, according to Ultimate Guide to NHIs, which shows how quickly delegated access expands beyond direct ownership.
A question worth separating out:
Q: What frameworks help teams control AI agent access and delegated identity?
A: OWASP NHI and NIST Zero Trust Architecture are the most relevant starting points because they both assume access must be continuously governed and tightly scoped. For agentic workflows, teams should extend those controls to per-call authorization, short-lived delegation, and clear audit trails across every upstream system the agent can reach.
👉 Read our full editorial: RFC 8693 token exchange is becoming the agent identity baseline
